nvidia/Llama-3.1-Minitron-4B-Width-Base download history
nvidia/Llama-3.1-Minitron-4B-Width-Base is a 4.5B-parameter text generation model by nvidia. In the last 30 days it was downloaded 4,163 times (744 in the last 7 days), and 89,604 times in total.
It ranks #12,856 on the Hub by monthly downloads and #3,298 among text generation models.
It has 197 likes.
157 models build on Llama-3.1-Minitron-4B-Width-Base: 121 quantized, 21 fine-tuned, 5 adapters and 10 merges. Together with the original they were downloaded 99,260 times in the last 30 days. See the Llama-3.1-Minitron-4B-Width-Base galaxy.
Most downloaded derivatives
- nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 (finetune), 6.4K downloads in 30 days
- bartowski/Llama-3.1-Minitron-4B-Width-Base-GGUF (quantized), 3.5K downloads in 30 days
- legraphista/Llama-3.1-Minitron-4B-Width-Base-GGUF (quantized), 2.4K downloads in 30 days
- Mungert/Llama-3.1-Nemotron-Nano-4B-v1.1-GGUF (quantized), 2.3K downloads in 30 days
- mradermacher/Llama-3.1-Minitron-4B-Width-Base-GGUF (quantized), 1.2K downloads in 30 days
- QuantFactory/MagpieLM-4B-SFT-v0.1-GGUF (quantized), 921 downloads in 30 days
- QuantFactory/magnum-v2-4b-GGUF (quantized), 600 downloads in 30 days
- anthracite-org/magnum-v2-4b (finetune), 377 downloads in 30 days
- SicariusSicariiStuff/Impish_LLAMA_4B (finetune), 157 downloads in 30 days
- psx7/llama4B (quantized), 148 downloads in 30 days
- NikolayKozloff/Llama-3.1-Minitron-4B-Width-Base-Q8_0-GGUF (quantized), 93 downloads in 30 days
- Magpie-Align/MagpieLM-4B-SFT-v0.1 (finetune), 58 downloads in 30 days
Open nvidia/Llama-3.1-Minitron-4B-Width-Base on Hugging Face